Fetal lung maturity assessment: A historic perspective and Non - invasive assessment using an automatic quantitative ultrasound analysis (a potentially useful clinical tool)

Amniotic fluid: its role in fetal development and beyond

Amniotic fluid is a complex biological medium that surrounds the fetus and offers not only mechanical protection but also provides nutrition and plays a critical role in normal fetal growth, organogenesis, and potentially fetal programming. Despite its importance, the biology of amniotic fluid has been understudied because of ethical and technical challenges in obtaining amniotic fluid samples from healthy human pregnancies, translational limitations of animal models to humans due to species-specific differences. Recent progress in understanding its dynamic physiology, composition, and clinical applications has advanced prenatal care and facilitated improved diagnostic and therapeutic strategies. As research continues to elucidate the complexities and evolutionary function of amniotic fluid, its increasingly recognized role in maternal-fetal medicine and its potential to transform clinical practice will only become more evident. The purpose of this review is to underscore the key roles of amniotic fluid in shaping fetal development and therapeutic potential.

IVIM-Morph: Motion-compensated quantitative Intra-voxel Incoherent Motion (IVIM) analysis for functional fetal lung maturity assessment from diffusion-weighted MRI data

Quantitative analysis of pseudo-diffusion in diffusion-weighted magnetic resonance imaging (DWI) data shows potential for assessing fetal lung maturation and generating valuable imaging biomarkers. Yet, the clinical utility of DWI data is hindered by unavoidable fetal motion during acquisition. We present IVIM-morph, a self-supervised deep neural network model for motion-corrected quantitative analysis of DWI data using the Intra-voxel Incoherent Motion (IVIM) model. IVIM-morph combines two sub-networks, a registration sub-network, and an IVIM model fitting sub-network, enabling simultaneous estimation of IVIM model parameters and motion. To promote physically plausible image registration, we introduce a biophysically informed loss function that effectively balances registration and model-fitting quality. We validated the efficacy of IVIM-morph by establishing a correlation between the predicted IVIM model parameters of the lung and gestational age (GA) using fetal DWI data of 39 subjects. Our approach was compared against six baseline methods: (1) no motion compensation, (2) affine registration of all DWI images to the initial image, (3) deformable registration of all DWI images to the initial image, (4) deformable registration of each DWI image to its preceding image in the sequence, (5) iterative deformable motion compensation combined with IVIM model parameter estimation, and (6) self-supervised deep-learning-based deformable registration. IVIM-morph exhibited a notably improved correlation with gestational age (GA) when performing in-vivo quantitative analysis of fetal lung DWI data during the canalicular phase. Specifically, over 2 test groups of cases, it achieved an Rf2 of 0.44 and 0.52, outperforming the values of 0.27 and 0.25, 0.25 and 0.00, 0.00 and 0.00, 0.38 and 0.00, and 0.07 and 0.14 obtained by other methods. IVIM-morph shows potential in developing valuable biomarkers for non-invasive assessment of fetal lung maturity with DWI data. Moreover, its adaptability opens the door to potential applications in other clinical contexts where motion compensation is essential for quantitative DWI analysis. The IVIM-morph code is readily available at: https://github.com/TechnionComputationalMRILab/qDWI-Morph.

[Application of Fetal Magnetic Resonance Imaging in Prognosis Assessment of Fetuses With Congenital Pulmonary Cystic Diseases]

Objective

The aim of this study is to explore the practical value of prenatal magnetic resonance imaging (MRI) in the assessment of congenital cystic lung disease in fetuses, to evaluate the relative size of the lesion and the status of lung development, and to make an attempt at utilizing the strength of MRI in post-processing to obtain assessment indicators of the size of the lesion and the status of lung development, with which predictions can be made for the prognosis that these fetuses may face after birth. We retrospectively collected and analyzed the data of fetuses diagnosed with congenital cystic lung disease. Prenatal ultrasound examination of these fetuses led to the diagnosis that they were suspected of having congenital cystic lung disease and the diagnosis was confirmed by subsequent prenatal MRI. The fetuses were followed up to track their condition at birth (postnatal respiratory distress, mechanical ventilation, etc.), whether the fetuses underwent surgical treatment, and the recovery of the fetuses after surgical treatment. The recovery of the fetuses was followed up to explore the feasibility of prenatal MRI examination to assess fetal congenital pulmonary cystic disease, and to preliminarily explore the predictive value of prenatal MRI for the prognosis of fetuses with congenital pulmonary cystic disease.

Methods

MRI fetal images were collected from pregnant women who attended the West China Second University Hospital of Sichuan University between May 2018 and March 2023 and who were diagnosed with fetal congenital pulmonary cystic disease by prenatal ultrasound and subsequent MRI. Fetal MRI images of congenital cystic lung disease were post-processed to obtain the fetal lung lesion volume, the fetal affected lung volume, the healthy lung volume, and the fetal head circumference measurements. The signal intensity of both lungs and livers, the lesion volume/the affected lung volume, the lesion volume/total lung volume, the cystic volume ratio (CVR), and the bilateral lung-liver signal intensity ratio were measured. The feasibility and value of MRI post-processing acquisition indexes for evaluating the prognosis of fetuses with congenital cystic lung disease were further analyzed by combining the follow-up results obtained 6 months after the birth of the fetus. Logistic regression models were used to quantify the differences in maternal age, gestational week at the time of MRI, CVR, and bilateral lung-to-liver signal intensity ratio, and to assess whether these metrics correlate with poor prognosis. Receiver operating characteristic (ROC) curves were used to assess the value of the parameters obtained by MRI calculations alone and in combination with multiple metrics for predicting poor prognosis after birth.

Results

We collected a total of 67 cases of fetuses diagnosed with congenital cystic lung disease by fetal MRI between May 2018 and March 2023, and excluded 6 cases with no normal lung tissue in the affected lungs, 11 cases of fetal induction, and 3 cases of loss of pregnancy. In the end, 47 cases of fetuses with congenital cystic lung disease were included, of which 30 cases had a good prognosis and 17 cases had a poor prognosis. The difference in the difference between the signal intensity ratios of the affected and healthy sides of the lungs and livers of the fetuses in the good prognosis group and that in the poor prognosis group was statistically significant (P<0.05), and the signal intensity ratio of the healthy side of the lungs and livers was higher than the signal intensity ratio of the affected side of the lungs and livers. Further analysis showed that CVR (odds ratio [OR]=1.058, 95% confidence interval [CI]: 1.014-1.104), and the difference between the lung-to-liver signal intensity ratios of the affected and healthy sides (OR=0.814, 95% CI: 0.700-0.947) were correlated with poor prognosis of birth in fetuses with congenital cystic lung disease. In addition, ROC curve analysis showed that the combined application of lesion volume/affected lung volume and the observed difference in the signal intensity ratio between the affected and healthy lungs and liver predicted the prognosis of children with congenital cystic lung disease more accurately than the single-parameter judgment did, with the area under the curve being 0.988, and the cut-off value being 0.33, which corresponded to a sensitivity of 100%, a specificity of 93.3%, and a 95% CI of 0.966-1.000.

Conclusions

Based on the MRI of fetuses with congenital cystic lung disease, we obtained information on lesion volume, lesion volume/affected lung volume, lesion volume/total lung volume, CVR, and bilateral lung-to-liver signal intensity ratio difference, all of which showing some clinical value in predicting the poor prognosis in fetuses with congenital cystic lung disease. Furthermore, among the combined indexes, the lesion volume/affected lung volume and bilateral lung-to-liver signal intensity ratio difference are more effective predictors for the poor prognosis of fetuses with congenital cystic lung disease, and show better efficacy in predicting the poor prognosis of fetuses with congenital cystic lung disease. This provides a new and effective predictive method for further assessment of pulmonary lung development in fetuses with congenital cystic lung disease, and helps improve the assessment and prediction of the prognosis of fetuses with congenital cystic lung disease.

[Histology of fetal lungs at different gestational age]

The lecture is devoted to the morphological characteristics of the maturation of lung tissue structures in the fetal period. Fetal histology of the lungs presents the intrauterine development of lung tissue in four successive stages: pseudoglandular, canalicular, saccular and alveolar, each has specific morphological criteria. The following morphological features are predetermined: the development of alveolar epithelium, the ratio of mesenchyme towards the area in alveolar spaces, the degree of proliferation and location of vessels of the microcirculatory bed towards prealveolar partitions. During the fetal period the alveolar columnar epithelium is flattened and differentiates into alveolocytes type I and II, the area of the mesenchyme gradually decreases and by the birth of a full-term newborn kid it is present mainly in the thickness between the alveolar septa, microcirculation vessels, initially laying deep in the thickness of the mesenchymal tissue, gradually proliferate, approach the pre-alveolar epithelium, channeling it with the formation of alveolar capillary membranes. Air exchange in the lung tissue is mainly provided with two factors: the presence of second-order alveolocytes capable of producing surfactant, and a sufficient formation of alveoli as well. This work summarizes the basics of fetal lung histology with the demonstration of histological preparations of the lungs at different stages of intrauterine development.

Enhancing Fetal Anomaly Detection in Ultrasonography Images: A Review of Machine Learning-Based Approaches

Fetal development is a critical phase in prenatal care, demanding the timely identification of anomalies in ultrasound images to safeguard the well-being of both the unborn child and the mother. Medical imaging has played a pivotal role in detecting fetal abnormalities and malformations. However, despite significant advances in ultrasound technology, the accurate identification of irregularities in prenatal images continues to pose considerable challenges, often necessitating substantial time and expertise from medical professionals. In this review, we go through recent developments in machine learning (ML) methods applied to fetal ultrasound images. Specifically, we focus on a range of ML algorithms employed in the context of fetal ultrasound, encompassing tasks such as image classification, object recognition, and segmentation. We highlight how these innovative approaches can enhance ultrasound-based fetal anomaly detection and provide insights for future research and clinical implementations. Furthermore, we emphasize the need for further research in this domain where future investigations can contribute to more effective ultrasound-based fetal anomaly detection.

Erythrocyte Membrane-Camouflaged Aggregation-Induced Emission Nanoparticles for Fetal Intestinal Maturation Assessment

Assessment of fetal maturity is essential for timely termination of pregnancy, especially in pregnant women with pregnancy complications. However, there is a lack of methods to assess the maturity of fetal intestinal function. Here, we constructed erythrocyte membrane-camouflaged aggregation-induced emission (AIE) nanoparticles. Nanocore is formed using a hollow mesoporous silicon nanobox (HMSN) of different particle sizes loaded with AIE luminogens -PyTPA (P), which are then co-extruded with erythrocyte membranes (M) to construct M@HMSN@P. The 100 nm M@HMSN@P has a more effective cellular uptake efficiency in vitro and in vivo. Swallowing and intestinal function in fetal mice mature with the increase in gestational age. After intrauterine injection of M@HMSN@P, they were swallowed and absorbed by fetal mice, and their swallowed and absorbed amount was positively correlated with the gestational age with a correlation coefficient of 0.9625. Using the M@HMSN@P (fluorescence intensity) in fetal mice, the gestational age can be imputed, and the difference between this imputed gestational age and the actual gestational age is less than 1 day. Importantly, M@HMSN@P has no side effect on the health status of pregnant and fetal mice, showing good biocompatibility. In conclusion, we constructed M@HMSN@P nanoparticles with different particle sizes and confirmed that the smaller size M@HMSN@P has more efficient absorption efficiency and it can assess fetal intestinal maturity by the intensity of the fluorescence signal.

Ultrasound-based radiomics technology in fetal lung texture analysis prediction of neonatal respiratory morbidity

To develop a novel method for predicting neonatal respiratory morbidity (NRM) by ultrasound-based radiomics technology. In this retrospective study, 430 high-throughput features per fetal-lung image were extracted from 295 fetal lung ultrasound images (four-chamber view) in 295 single pregnancies. Images had been obtained between 28⁺³ and 37⁺⁶ weeks of gestation within 72 h before delivery. A machine-learning model built by RUSBoost (Random under-sampling with AdaBoost) architecture was created using 20 radiomics features extracted from the images and 2 clinical features (gestational age and pregnancy complications) to predict the possibility of NRM. Of the 295 standard fetal lung ultrasound images included, 210 in the training set and 85 in the testing set. The overall performance of the neonatal respiratory morbidity prediction model achieved AUC of 0.88 (95% CI 0.83–0.92) in the training set and 0.83 (95% CI 0.79–0.97) in the testing set, sensitivity of 84.31% (95% CI 79.06–89.44%) in the training set and 77.78% (95% CI 68.30–87.43%) in the testing set, specificity of 81.13% (95% CI 78.16–84.07%) in the training set and 82.09% (95% CI 77.65–86.62%) in the testing set, and accuracy of 81.90% (95% CI 79.34–84.41%) in the training set and 81.18% (95% CI 77.33–85.12%) in the testing set. Ultrasound-based radiomics technology can be used to predict NRM. The results of this study may provide a novel method for non-invasive approaches for the prenatal prediction of NRM.

Ultrasound Multiparametric Assessment of the Impact of Hypertensive Disorders of Pregnancy on Fetal Cardiac Function and Growth and Development

Objective

To evaluate the ultrasound multiparametric assessment of the impact of hypertensive disorders of pregnancy (HDP) on fetal cardiac function and growth and development.

Methods

In this prospective study, 98 cases of HDP treated in our institution were recruited into a study group, and 100 pregnant women with healthy singleton pregnancies were included in a control group. All eligible patients were also assigned to either study group A (HDP fetuses with growth restriction) or study group B (HDP fetuses with normal growth). Fetal echocardiography was performed on all eligible participants to obtain hemodynamic and cardiac function parameters for the evaluation of fetal growth and development, and the impact of HDP on fetal heart function and growth and development was analyzed.

Results

HDP fetuses were associated with smaller head circumference, biparietal diameter, femoral length, and abdominal circumference versus healthy fetuses. The study group had a higher resistance index (RI) and pulsatility index (PI) of umbilical artery (UA), ductus venous (DV), pulmonary vein (PV), and lower RI and PI of aortic isthmus (AoI) than the control group. The study group showed higher left and right ventricular isovolumic contraction time (IVCT), isovolumic relaxation time (IVRT), and myocardial performance index (MPI) values and lower mitral and tricuspid E wave and E/A values than the control group. The systolic blood pressure was positively correlated with PI, RI of UA, DV, and PV, and left and right ventricular IVCT, IVRT, and MPI and negatively correlated with PI and RI of AoI and mitral and tricuspid E wave and E/A values of HDP fetuses. The peak systolic/diastolic flow rate (S/D), PI, and RI of umbilical blood flow in study group A were higher than those in study group B. Umbilical blood flow S/D showed the highest AUC and specificity for predicting fetal growth restriction, and PI had the highest sensitivity for predicting fetal growth restriction.

Conclusion

HDP compromises fetal cardiac function and growth, and ultrasound multiparametric assessment provides accurate detection of fetal cardiac function and hemodynamics changes. The patient's condition can be monitored through the assessment of ultrasound parameters of fetal growth and development.